Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4848 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0056. Min Range: -7.0056
Max Act: 7.0056. Min Act: -0.1700
Data Index: 2754172 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.8493. Min Act: -0.1700
Data Index: 7675736 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.6931. Min Act: -0.1700
Data Index: 2018933 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.5681. Min Act: -0.1700
Data Index: 7910342 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.5368. Min Act: -0.1700
Data Index: 3257597 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.5368. Min Act: -0.1700
Data Index: 3217857 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4743. Min Act: -0.1700
Data Index: 2814344 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4431. Min Act: -0.1700
Data Index: 7870749 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4431. Min Act: -0.1700
Data Index: 4974704 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4431. Min Act: -0.1700
Data Index: 8653691 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4431. Min Act: -0.1700
Data Index: 7876547 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.4118. Min Act: -0.1700
Data Index: 8078073 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3806. Min Act: -0.1700
Data Index: 5710521 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3493. Min Act: -0.1700
Data Index: 6731078 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3181. Min Act: -0.1700
Data Index: 5636677 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3181. Min Act: -0.1700
Data Index: 2444693 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3493. Min Act: -0.1700
Data Index: 4627571 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3493. Min Act: -0.1700
Data Index: 6577431 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3493. Min Act: -0.1700
Data Index: 677546 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0056. Min Range: -7.0056
Max Act: 6.3181. Min Act: -0.1700
Data Index: 2754171 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #19